examples
examples copied to clipboard
qdrant
A collection of examples and tutorials for Qdrant vector search engine
This PR adds an end-to-end example demonstrating using Qdrant for semantic search over YouTube video transcripts combined with OpenAI to generate new video ideas based on past content. Specifically, it...
Since the zip function adopts the length of the shorter iterable, information loss can occur. Therefore, it is necessary to ensure that the number of embeddings matches the number of...
Hi I added an example about nested prefetch used as reranker. @kacperlukawski
Updating the graphrag demo to include hierarchal ontology with communities and super communities-https://github.com/DenizAskinIBM/Knowledge-Graph/blob/main/GraphGeneration/Tavily_Community_of_Communities.py
This is an umbrella PR for all the changes required to automate converting Jupyter notebooks into Hugo Markdown files. Eventually, the examples repo will act as a source for the...
This PR implements the example from the "Automate filtering with LLMs" tutorial. See: https://github.com/qdrant/landing_page/pull/1330
- [ ] Notebook - [ ] Readme - [X] Python Script - [X] Requirements - [ ] Dataset
## Summary This PR introduces a new tutorial: **Agentic PDF RAG System**. ### Key changes: - Added `Agentic_PDF_RAG.ipynb` notebook under `Agentic-langGraph-RAG/` - Created a detailed `readme.md` explaining the system architecture...
From `graphrag_neo4j/graphrag.py`: in function [`ingest_to_qdrant`](https://github.com/qdrant/examples/blob/b3c4b28f66c8cf2a9674bb4491f3f057a1e51237/graphrag_neo4j/graphrag.py#L158) it seems like the `embedding` being upserted does not correspond to the `node_id`. Each `embedding` is generated from each line of `raw_data`, while `node_id` is...
